Paul Christiano - Wikipedia

Paul Christiano - Wikipedia 

 

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 Jump to content 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

 From Wikipedia, the free encyclopedia 
 
 
 
 
 
 American AI safety researcher 
 For the choreographer, see Paul Christiano (choreographer) . 
 Paul Christiano Education Massachusetts Institute of Technology (BS)
 University of California, Berkeley (PhD)
 Known for AI alignment 
 Reinforcement learning from human feedback 
 Scientific career Institutions NIST 
 OpenAI 
 Alignment Research Center 
 Thesis Manipulation-resistant online learning   (2017) Doctoral advisor Umesh Vazirani 
 Website paulfchristiano .com 
 Paul Christiano is an American researcher in the field of artificial intelligence (AI), with a specific focus on AI alignment , which is the subfield of AI safety research that aims to steer AI systems toward human interests. [ 1 ] He serves as the Head of Safety for the Center for AI Standards and Innovation inside NIST . [ 2 ] He formerly led the language model alignment team at OpenAI and became founder and head of the non-profit Alignment Research Center (ARC), which works on theoretical AI alignment and evaluations of machine learning models. [ 3 ] [ 4 ] In 2023, Christiano was named as one of the TIME 100 Most Influential People in AI ( TIME 100 AI). [ 4 ] [ 5 ] 

 In September 2023, Christiano was appointed to the UK government's Frontier AI Taskforce advisory board. [ 6 ] Before working at the Center for AI Standards and Innovation, he was an initial trustee on Anthropic 's Long-Term Benefit Trust. [ 7 ] [ 8 ] 

 
 Education

 [ edit ] 
 Christiano attended the Harker School in San Jose, California. [ 9 ] He competed on the U.S. team and won a silver medal at the 49th International Mathematics Olympiad (IMO) in 2008. [ 9 ] [ 10 ] 

 In 2012, Christiano graduated from the Massachusetts Institute of Technology (MIT) with a degree in mathematics. [ 11 ] [ 12 ] At MIT, he researched data structures, quantum cryptography, and combinatorial optimization. [ 12 ] 

 He then went on to complete a PhD at the University of California, Berkeley . [ 13 ] While at Berkeley, Christiano collaborated with researcher Katja Grace on AI Impacts, co-developing a preliminary methodology for comparing supercomputers to brains, using traversed edges per second (TEPS). [ 14 ] He also experimented with putting Carl Shulman 's donor lottery theory into practice, raising nearly $50,000 in a pool to be donated to a single charity. [ 15 ] 

 Career

 [ edit ] 
 At OpenAI, Christiano co-authored the paper "Deep Reinforcement Learning from Human Preferences" (2017) and other works developing reinforcement learning from human feedback (RLHF). [ 16 ] [ 17 ] He is considered one of the principal architects of R

... (truncated, 13 KB total)